Ordinal Measures for Image Correspondence

By D. Bhat, Shree K. Nayar. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, methodology): “pondences is extremely problematic due to local appearance changes or self-occlusions. Moreover, lack of texture on objects and specular re ections also make the feature matching problem very dicult [10,11]. In order to circumvent issues related to large baselines or non-Lambertian surfaces, 3D volu”
Visual features of intermediate complexity and their use in classification (2002, methodology): “We also tested normalized cross-correlation and the ordinal measure (in ref”
Comparison of sequence matching techniques for video copy detection (2001, unknown): “NT Fnr(?) = Fn NT ( 9 ) The ROC curves are computed by varying ? from its minimum value to its maximum with an increment of 5%. A good ROC curve lies very close to the axes, i.e., there is some threshold value for which both Fpr and Fnr are very close to zero.”
Ordinal Measures for Iris Recognition (2009, methodology): “Bhat and Nayar employed the rank permutation of pixel intensity values in image windows for stereocorrespondence [27].”
Advances in Computational Stereo (2003, background): “To remedy this problem, Bhat and Nayar [7] propose an alternative ordinal measure based on the distance between rank value positions rather than the rank values themselves.”
Template Matching Techniques in Computer Vision: Theory and Practice (2009, unknown): “get(img[[3]], animask (0 ,0 ,1201 ,256))) 6 imgB <- tm.”
Evaluation of Stereo Matching Costs on Images with Radiometric Differences (2009, unknown): “A further significant speedup is expected by a recursive implementation using a heap tree as data structure [14].”
CENTRIST: A Visual Descriptor for Scene Categorization (2011, background): “ordinal measures [31]), Census Transform is robust to illumination changes, gamma variations, etc.”
Ordinal palmprint represention for personal identification [represention read representation] (2005, methodology): “Bhat and Nayar employed the rank permutation of pixel intensity values in image windows for stereo correspondence [16].”
Video copy detection: a comparative study (2007, methodology): “This ordinal measure was originally proposed by Bhat and Nayar [2] for computing image correspondences, and adapted by Mohan in [19] for video purposes.”